Design robust graph neural networks with PyTorch Geometric by combining graph theory and neural networks with the latest developments and appsKey FeaturesImplement state-of-the-art graph neural network architectures in PythonCreate your own graph datasets from tabular dataBuild powerful traffic forecasting, recommender systems, and anomaly detection applicationsBook DescriptionGraph neural networks are a highly effective tool for analyzing data that can be represented as a graph, such as social networks, chemical compounds, or transportation networks. The past few years have seen an explosion in the use of graph neural networks, with their application ranging from natural language processing and computer vision to recommendation systems and drug discovery.Hands-On Graph Neural Networks Using Python begins with the fundamentals of graph theory and shows you how to create graph datasets from tabular data. As you advance, you'll explore major graph neural network architectures and learn essential concepts such as graph convolution, self-attention, link prediction, and heterogeneous graphs. Finally, the book proposes applications to solve real-life problems, enabling you to build a professional portfolio. The code is readily available online and can be easily adapted to other datasets and apps.By the end of this book, you'll have learned to create graph datasets, implement graph neural networks using Python and PyTorch Geometric, and apply them to solve real-world problems, along with building and training graph neural network models for node and graph classification, link prediction, and much more.What you will learnUnderstand the fundamental concepts of graph neural networksImplement graph neural networks using Python and PyTorch GeometricClassify nodes, graphs, and edges using millions of samplesPredict and generate realistic graph topologiesCombine heterogeneous sources to improve performanceForecast future events using topological informationApply graph neural networks to solve real-world problemsWho this book is forThis book is for machine learning practitioners and data scientists interested in learning about graph neural networks and their applications, as well as students looking for a comprehensive reference on this rapidly growing field. Whether you're new to graph neural networks or looking to take your knowledge to the next level, this book has something for you. Basic knowledge of machine learning and Python programming will help you get the most out of this book.About the AuthorMaxime Labonne is currently a senior applied researcher at Airbus. He received a M.Sc. degree in computer science from INSA CVL, and a Ph.D. in machine learning and cyber security from the Polytechnic Institute of Paris. During his career, he worked on computer networks and the problem of representation learning, which led him to explore graph neural networks. He applied this knowledge to various industrial projects, including intrusion detection, satellite communications, quantum networks, and AI-powered aircrafts. He is now an active graph neural network evangelist through Twitter and his personal blog. Table of ContentsGetting Started with Graph LearningGraph Theory for Graph Neural NetworksCreating Node Representations with DeepWalkImproving Embeddings with Biased Random Walks in Node2VecIncluding Node Features with Vanilla Neural NetworksIntroducing Graph Convolutional NetworksGraph Attention NetworksScaling Graph Neural Networks with GraphSAGEDefining Expressiveness for Graph ClassificationPredicting Links with Graph Neural NetworksGenerating Graphs Using Graph Neural NetworksLearning from Heterogeneous GraphsTemporal Graph Neural NetworksExplaining Graph Neural NetworksForecasting Traffic Using A3T-GCNDetecting Anomalies Using Heterogeneous Graph Neural NetworksBuilding a Recommender System Using LightGCNUnlocking the Potential of Graph Neural Networks for Real-Word Applications